© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2133
    Prev
    Next
    INDEX
    Explanations

    first occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ys
    -0.24
    åı¦ä¸ĢåįĬ
    -0.23
    æ¼Ĥ
    -0.22
    strcasecmp
    -0.22
    .tagName
    -0.22
    others
    -0.22
    try
    -0.22
    Tre
    -0.21
     Treasure
    -0.21
    èĭ¥
    -0.21
    POSITIVE LOGITS
     occasions
    0.26
    ä¸įå°ı
    0.25
     ocas
    0.24
     ÑģлÑĥÑĩа
    0.23
     Rico
    0.23
    åıijçĶŁåľ¨
    0.23
    ime
    0.23
     INCIDENT
    0.23
     Ensemble
    0.23
    æľīä¸įå°ij
    0.23
    Activations Density 0.039%

    No Known Activations